Colonnade: A Reconfigurable SRAM-Based Digital Bit-Serial Compute-In-Memory Macro for Processing Neural Networks.
Hyunjoon KimTaegeun YooTony Tae-Hyoung KimBongjin KimPublished in: IEEE J. Solid State Circuits (2021)
Keyphrases
- random access memory
- neural network
- design considerations
- low cost
- auto associative
- low voltage
- associative memory
- compute intensive
- real time
- memory requirements
- data processing
- genetic algorithm
- pattern recognition
- memory management
- random access
- computational power
- recurrent neural networks
- data acquisition
- main memory
- self organizing maps
- processing elements
- artificial neural networks
- memory access
- hash table
- neural network model
- reconfigurable hardware
- power reduction
- virtual memory
- fuzzy logic
- neural nets
- power consumption
- memory usage
- data transmission
- hardware implementation